Amanvir Parhar
@amanvir.bsky.social
building azigy.com • studying @ umd cs • making things amanvir.com • writing venusgirdle.com
I created a 3D visualization that shows *every* attention weight matrix within GPT-2 as the model generates tokens!
April 20, 2025 at 5:31 PM
I created a 3D visualization that shows *every* attention weight matrix within GPT-2 as the model generates tokens!
Over the past few days, I worked on creating a text animation effect using Dawkins' weasel, a computer simulation devised by evolutionary biologist Richard Dawkins in the 1980s.
March 18, 2025 at 11:02 AM
Over the past few days, I worked on creating a text animation effect using Dawkins' weasel, a computer simulation devised by evolutionary biologist Richard Dawkins in the 1980s.
I built an ESP32-based DNS sinkhole that stops you from doomscrolling!
This was a really fun project that I wrote a detailed blog post about.
In it, I document my experience building this thing, and I also share what I’ve learned about DNS, networking, and low-level programming along the way ⬇️
This was a really fun project that I wrote a detailed blog post about.
In it, I document my experience building this thing, and I also share what I’ve learned about DNS, networking, and low-level programming along the way ⬇️
February 28, 2025 at 10:35 AM
I built an ESP32-based DNS sinkhole that stops you from doomscrolling!
This was a really fun project that I wrote a detailed blog post about.
In it, I document my experience building this thing, and I also share what I’ve learned about DNS, networking, and low-level programming along the way ⬇️
This was a really fun project that I wrote a detailed blog post about.
In it, I document my experience building this thing, and I also share what I’ve learned about DNS, networking, and low-level programming along the way ⬇️
I wrote a script that uses Google’s Gemini-1.5-Flash model to fix typesetting and formatting issues in public domain eBooks from Project Gutenberg.
It’s open source, and it works thanks to Gemini’s insanely long context window (1M+ tokens)!
A thread 🧵 ⬇️
It’s open source, and it works thanks to Gemini’s insanely long context window (1M+ tokens)!
A thread 🧵 ⬇️
February 12, 2025 at 11:33 PM
I wrote a script that uses Google’s Gemini-1.5-Flash model to fix typesetting and formatting issues in public domain eBooks from Project Gutenberg.
It’s open source, and it works thanks to Gemini’s insanely long context window (1M+ tokens)!
A thread 🧵 ⬇️
It’s open source, and it works thanks to Gemini’s insanely long context window (1M+ tokens)!
A thread 🧵 ⬇️